Adaptive Integration of Survey Data with Other Information Sources

• Activity Number: 160
• Type: Topic Contributed
• Date/Time: Monday, August 4, 2014 : 10:30 AM to 12:20 PM
• Sponsor: Survey Research Methods Section
• Author(s): John Eltinge*+
• Companies: Bureau of Labor Statistics
• Keywords: administrative record and transaction data ; big data ; multiple-frame-multiple-mode ; non-designed data ; organic data ; propensity models

Abstract

In recent years, statistical organizations have developed increasing interest in the integration of customary sample survey data with information from other sources. Examples of these sources include administrative records, commercial transaction records, and social media traces; and sometimes have labels like "organic data," "non-designed data" and "big data." For some cases, methods for integration of these data sources can be based on extensions of previously developed methods for propensity modeling and for multiple-frame-multiple mode surveys. This paper discusses these integration methods, with special emphasis on adaptive use of information on microdata quality and costs associated with a given data source.